Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4325 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.7503. Min Range: -3.7503

Max Act: 3.7503. Min Act: -0.0000

Data Index: 468371 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 3.7503. Min Range: -3.7503

Max Act: 3.5964. Min Act: -0.0000

Data Index: 1318944 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 3.7503. Min Range: -3.7503

Max Act: 3.5957. Min Act: -0.0000

Data Index: 1295627 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 3.7503. Min Range: -3.7503

Max Act: 3.5023. Min Act: -0.0000

Data Index: 471017 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 3.7503. Min Range: -3.7503

Max Act: 3.1937. Min Act: -0.0000

Data Index: 1209002 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 3.7503. Min Range: -3.7503

Max Act: 3.1901. Min Act: -0.0000

Data Index: 198093 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 3.7503. Min Range: -3.7503

Max Act: 3.3498. Min Act: -0.0000

Data Index: 23257 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 3.7503. Min Range: -3.7503

Max Act: 3.2744. Min Act: -0.0000

Data Index: 466119 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 3.7503. Min Range: -3.7503

Max Act: 2.9739. Min Act: -0.0000

Data Index: 306427 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 3.7503. Min Range: -3.7503

Max Act: 3.0149. Min Act: -0.0000

Data Index: 683459 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 3.7503. Min Range: -3.7503

Max Act: 2.9543. Min Act: -0.0000

Data Index: 1354279 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 3.7503. Min Range: -3.7503

Max Act: 2.6774. Min Act: -0.0000

Data Index: 479840 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 3.7503. Min Range: -3.7503

Max Act: 2.7738. Min Act: -0.0000

Data Index: 1226283 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 3.7503. Min Range: -3.7503

Max Act: 2.9107. Min Act: -0.0000

Data Index: 246450 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 3.7503. Min Range: -3.7503

Max Act: 2.9859. Min Act: -0.0000

Data Index: 931046 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 3.7503. Min Range: -3.7503

Max Act: 2.8388. Min Act: -0.0000

Data Index: 264589 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 3.7503. Min Range: -3.7503

Max Act: 2.6660. Min Act: -0.0000

Data Index: 977104 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 3.7503. Min Range: -3.7503

Max Act: 2.6890. Min Act: -0.0000

Data Index: 39343 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 3.7503. Min Range: -3.7503

Max Act: 2.6576. Min Act: -0.0000

Data Index: 783086 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 3.7503. Min Range: -3.7503

Max Act: 2.8112. Min Act: -0.0000

Data Index: 969405 (C4 (Web Text))

Max Activating Token Index: 278